convert dataset to coco/voc format

[Cancer Research] 3D Deep Learning from CT Scans Predicts Tumor Invasiveness of Subcentimeter Pulmonary Adenocarcinomas

Simple implementation of augmentation for small object detection

Res2Net architecture with improved stem and Mish activation function

SIIM-ACR Pneumothorax Segmentation first place solution

Composite Backbone Network

最严垃圾分类政策自7月1日颁布，如何进行垃圾分类已经成为居民生活的灵魂拷问。但是，没关系！AI在垃圾分类的应用可以成为居民的得力助手。本次垃圾分类挑战杯，目的在于构建基于深度学习技术的图像分类模型，实现垃圾图片类别的精准识别，大赛参考深圳垃圾分类标准，按可回收物、厨余垃圾、有害垃圾和其他垃圾四项分类。

WACV18 paper "DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification"

CenterNet / FCOS_PLUS/MatrixNets implemented by mmdetection

Rscup2019 Object Detection Track 3th Solution

Many studies have shown that the performance on deep learning is significantly affected by volume of training data. The MedicalNet project provides a series of 3D-ResNet pre-trained models and rela…

Learning Data Augmentation Strategies for Object Detection in numpy

验证码识别

全球数据智能大赛赛场一——肺部CT多病种智能诊断

[MICCAI' 19] NoduleNet: Decoupled False Positive Reduction for Pulmonary Nodule Detection and Segmentation

rscup2019，分类赛道

rscup: 遥感图像场景分类

DeepSEED: 3D Squeeze-and-Excitation Encoder-Decoder ConvNets for Pulmonary Nodule Detection

Lightweight models for real-time semantic segmentation(include mobilenetv1-v3, shufflenetv1-v2, igcv3, efficientnet).

see details in configs/retinanet_se154_fpn_1x.py

DataFountain-基于虚拟仿真环境下的自动驾驶交通标志识别 4th

A PyTorch implementation of EfficientNet

winning sloution of Digtial Manfacturing Algorithm Competition II of JinNan Tianjin

A Keras implementation of MobileNetV3.

An example project of how to use a U-Net for segmentation on medical images with PyTorch.